{"id":"W4417130675","doi":"10.2139/ssrn.5887028","title":"MAC: Multi-Agent LLM Coder is All You Need","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Correctness; Robustness (evolution); Coding (social sciences); Code (set theory); Inference; Reliability (semiconductor)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001795652,0.0009471027,0.0009019807,0.0007366234,0.0008264309,0.002324251,0.001472885,0.001739813,0.07936697],"category_scores_gemma":[0.01176845,0.0005661635,0.000517618,0.0004608799,0.0006769461,0.002941394,0.00230666,0.003002937,0.05223203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007014718,"about_ca_system_score_gemma":0.001217377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001832405,"about_ca_topic_score_gemma":0.001890352,"domain_scores_codex":[0.9988968,0.0003041271,0.0000851138,0.0001800109,0.000379458,0.000154362],"domain_scores_gemma":[0.9946288,0.001385118,0.0003271885,0.001525638,0.001542186,0.0005910126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001300673,0.0002130551,0.001350816,0.0004189282,0.00009260198,0.0003469878,0.0003667852,0.0123963,0.01204495,0.04763167,0.5876141,0.3362231],"study_design_scores_gemma":[0.000470096,0.0002042269,0.0007432401,0.0002421419,0.00006306602,0.0003753263,0.0001233749,0.3378702,0.02744409,0.0690342,0.563264,0.0001659647],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.006563183,0.0004564998,0.6491752,0.005468188,0.001982326,0.0003257007,0.003316937,0.2919951,0.04071681],"genre_scores_gemma":[0.2759843,0.0006888412,0.526742,0.00622621,0.001739076,0.001446786,0.006152554,0.05129705,0.1297233],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.07936697,"threshold_uncertainty_score":0.2655089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03289518674378736,"score_gpt":0.2928385054906594,"score_spread":0.259943318746872,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}